The goal of this project is to compare methods for imputing missing data, specifically in the case of clustered data. Data were simulated for both binary and continuous outcomes, in sample sizes of 200, 500 or 1000, and with either 20% or 40% missingness. Methods of imputation were compared for each scenario in terms of relevant model fit statistics, bias, and computation time. The results are as follows:
—
—
—
—
—
—
—
—
—
—
## `summarise()` has grouped output by 'type', 'n_subj', 'miss_prob'. You can
## override using the `.groups` argument.
| Method | mse | mae | bias | pfc |
|---|---|---|---|---|
| Binary, n=200, Missing Probability = 0.2 | ||||
| jomo | 0.23 (0.02) | 0.15 (0.01) | -0.00 (0.01) | 0.09 (0.01) |
| knn | 0.16 (0.01) | 0.13 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| merf | 0.14 (0.01) | 0.12 (0.01) | 0.00 (0.01) | 0.08 (0.00) |
| mice_freq | 0.23 (0.02) | 0.15 (0.01) | -0.00 (0.01) | 0.09 (0.01) |
| mice_pmm | 0.22 (0.02) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| missforest | 0.12 (0.01) | 0.11 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| missranger | 0.23 (0.02) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| mixgb | 0.15 (0.01) | 0.12 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| Binary, n=200, Missing Probability = 0.4 | ||||
| jomo | 0.50 (0.03) | 0.32 (0.01) | -0.00 (0.02) | 0.19 (0.01) |
| knn | 0.34 (0.02) | 0.26 (0.01) | 0.00 (0.02) | 0.18 (0.01) |
| merf | 0.35 (0.03) | 0.26 (0.01) | 0.00 (0.02) | 0.17 (0.01) |
| mice_freq | 0.50 (0.03) | 0.32 (0.01) | -0.00 (0.02) | 0.19 (0.01) |
| mice_pmm | 0.48 (0.03) | 0.31 (0.01) | -0.00 (0.02) | 0.19 (0.01) |
| missforest | 0.30 (0.02) | 0.24 (0.01) | -0.00 (0.03) | 0.18 (0.01) |
| missranger | 0.50 (0.03) | 0.31 (0.01) | 0.00 (0.02) | 0.19 (0.01) |
| mixgb | 0.38 (0.03) | 0.27 (0.01) | -0.00 (0.02) | 0.18 (0.01) |
| Binary, n=500, Missing Probability = 0.2 | ||||
| jomo | 0.23 (0.01) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.00) |
| knn | 0.16 (0.01) | 0.13 (0.00) | 0.00 (0.01) | 0.09 (0.00) |
| merf | 0.14 (0.01) | 0.12 (0.00) | 0.00 (0.01) | 0.08 (0.00) |
| mice_freq | 0.23 (0.01) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.00) |
| mice_pmm | 0.22 (0.01) | 0.15 (0.01) | -0.00 (0.01) | 0.09 (0.00) |
| missforest | 0.12 (0.01) | 0.11 (0.00) | 0.00 (0.01) | 0.08 (0.00) |
| missranger | 0.23 (0.01) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| mixgb | 0.14 (0.01) | 0.12 (0.00) | 0.00 (0.01) | 0.09 (0.00) |
| Binary, n=500, Missing Probability = 0.4 | ||||
| jomo | 0.49 (0.02) | 0.31 (0.01) | -0.00 (0.01) | 0.19 (0.00) |
| knn | 0.34 (0.01) | 0.26 (0.01) | 0.00 (0.01) | 0.18 (0.00) |
| merf | 0.37 (0.02) | 0.27 (0.01) | 0.00 (0.02) | 0.17 (0.00) |
| mice_freq | 0.49 (0.02) | 0.31 (0.01) | -0.00 (0.01) | 0.19 (0.00) |
| mice_pmm | 0.48 (0.02) | 0.31 (0.01) | 0.00 (0.01) | 0.19 (0.00) |
| missforest | 0.30 (0.02) | 0.24 (0.01) | 0.00 (0.02) | 0.17 (0.01) |
| missranger | 0.49 (0.02) | 0.31 (0.01) | 0.00 (0.01) | 0.19 (0.01) |
| mixgb | 0.35 (0.02) | 0.26 (0.01) | 0.00 (0.02) | 0.18 (0.00) |
| Binary, n=1000, Missing Probability = 0.2 | ||||
| jomo | 0.22 (0.01) | 0.15 (0.00) | -0.00 (0.00) | 0.09 (0.00) |
| knn | 0.16 (0.01) | 0.13 (0.00) | -0.00 (0.00) | 0.09 (0.00) |
| merf | 0.15 (0.01) | 0.12 (0.00) | 0.00 (0.00) | 0.08 (0.00) |
| mice_freq | 0.22 (0.01) | 0.15 (0.00) | -0.00 (0.00) | 0.09 (0.00) |
| mice_pmm | 0.22 (0.01) | 0.15 (0.00) | 0.00 (0.00) | 0.09 (0.00) |
| missforest | 0.12 (0.01) | 0.11 (0.00) | 0.00 (0.00) | 0.08 (0.00) |
| missranger | 0.23 (0.01) | 0.15 (0.00) | 0.00 (0.00) | 0.09 (0.01) |
| mixgb | 0.13 (0.01) | 0.11 (0.00) | -0.00 (0.00) | 0.09 (0.00) |
| Binary, n=1000, Missing Probability = 0.4 | ||||
| jomo | 0.49 (0.02) | 0.31 (0.01) | -0.00 (0.01) | 0.19 (0.00) |
| knn | 0.34 (0.01) | 0.26 (0.00) | -0.00 (0.01) | 0.18 (0.00) |
| merf | 0.38 (0.02) | 0.27 (0.01) | 0.00 (0.01) | 0.17 (0.00) |
| mice_freq | 0.48 (0.01) | 0.31 (0.01) | -0.00 (0.01) | 0.19 (0.00) |
| mice_pmm | 0.48 (0.01) | 0.31 (0.01) | -0.00 (0.01) | 0.19 (0.00) |
| missforest | 0.30 (0.01) | 0.24 (0.01) | 0.00 (0.02) | 0.17 (0.00) |
| missranger | 0.49 (0.01) | 0.31 (0.01) | 0.00 (0.01) | 0.19 (0.01) |
| mixgb | 0.33 (0.02) | 0.25 (0.01) | 0.00 (0.01) | 0.17 (0.00) |
## `summarise()` has grouped output by 'type', 'n_subj', 'miss_prob'. You can
## override using the `.groups` argument.
| Method | mse | mae | bias | pfc |
|---|---|---|---|---|
| Continuous, n=200, Missing Probability = 0.2 | ||||
| jomo | 0.20 (0.02) | 0.14 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| knn | 0.16 (0.01) | 0.13 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| merf | 0.14 (0.01) | 0.12 (0.01) | 0.00 (0.01) | 0.08 (0.01) |
| mice_freq | 0.21 (0.02) | 0.14 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| mice_pmm | 0.20 (0.02) | 0.14 (0.01) | -0.00 (0.01) | 0.09 (0.01) |
| missforest | 0.12 (0.01) | 0.11 (0.01) | 0.00 (0.01) | 0.08 (0.01) |
| missranger | 0.23 (0.02) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| mixgb | 0.14 (0.01) | 0.12 (0.01) | 0.00 (0.01) | 0.08 (0.01) |
| Continuous, n=200, Missing Probability = 0.4 | ||||
| jomo | 0.46 (0.03) | 0.30 (0.01) | -0.00 (0.02) | 0.17 (0.01) |
| knn | 0.34 (0.02) | 0.26 (0.01) | 0.00 (0.02) | 0.18 (0.01) |
| merf | 0.34 (0.03) | 0.26 (0.01) | 0.01 (0.03) | 0.16 (0.01) |
| mice_freq | 0.46 (0.03) | 0.30 (0.01) | -0.00 (0.02) | 0.17 (0.01) |
| mice_pmm | 0.45 (0.03) | 0.30 (0.01) | 0.00 (0.02) | 0.17 (0.01) |
| missforest | 0.29 (0.02) | 0.24 (0.01) | 0.01 (0.03) | 0.17 (0.01) |
| missranger | 0.49 (0.03) | 0.31 (0.01) | 0.01 (0.02) | 0.19 (0.01) |
| mixgb | 0.35 (0.03) | 0.26 (0.01) | 0.00 (0.02) | 0.17 (0.01) |
| Continuous, n=500, Missing Probability = 0.2 | ||||
| jomo | 0.20 (0.01) | 0.14 (0.01) | 0.00 (0.01) | 0.09 (0.00) |
| knn | 0.16 (0.01) | 0.13 (0.00) | 0.00 (0.01) | 0.09 (0.00) |
| merf | 0.14 (0.01) | 0.12 (0.00) | 0.00 (0.01) | 0.08 (0.00) |
| mice_freq | 0.20 (0.01) | 0.14 (0.01) | 0.00 (0.01) | 0.09 (0.00) |
| mice_pmm | 0.20 (0.01) | 0.14 (0.00) | -0.00 (0.01) | 0.09 (0.00) |
| missforest | 0.12 (0.01) | 0.11 (0.00) | 0.00 (0.01) | 0.08 (0.00) |
| missranger | 0.22 (0.01) | 0.15 (0.01) | 0.00 (0.01) | 0.09 (0.01) |
| mixgb | 0.12 (0.01) | 0.11 (0.00) | 0.00 (0.01) | 0.08 (0.00) |
| Continuous, n=500, Missing Probability = 0.4 | ||||
| jomo | 0.44 (0.02) | 0.30 (0.01) | 0.00 (0.01) | 0.17 (0.00) |
| knn | 0.33 (0.01) | 0.26 (0.01) | 0.00 (0.01) | 0.18 (0.00) |
| merf | 0.35 (0.02) | 0.26 (0.01) | 0.01 (0.02) | 0.16 (0.00) |
| mice_freq | 0.45 (0.02) | 0.30 (0.01) | -0.00 (0.01) | 0.17 (0.00) |
| mice_pmm | 0.44 (0.02) | 0.29 (0.01) | 0.00 (0.01) | 0.17 (0.00) |
| missforest | 0.29 (0.02) | 0.24 (0.01) | 0.01 (0.02) | 0.17 (0.01) |
| missranger | 0.48 (0.02) | 0.31 (0.01) | 0.01 (0.01) | 0.19 (0.01) |
| mixgb | 0.33 (0.02) | 0.25 (0.01) | 0.00 (0.01) | 0.16 (0.00) |
| Continuous, n=1000, Missing Probability = 0.2 | ||||
| jomo | 0.20 (0.01) | 0.14 (0.00) | 0.00 (0.00) | 0.09 (0.00) |
| knn | 0.16 (0.01) | 0.13 (0.00) | 0.00 (0.00) | 0.09 (0.00) |
| merf | 0.14 (0.01) | 0.12 (0.00) | 0.00 (0.00) | 0.08 (0.00) |
| mice_freq | 0.20 (0.01) | 0.14 (0.00) | 0.00 (0.00) | 0.09 (0.00) |
| mice_pmm | 0.20 (0.01) | 0.14 (0.00) | 0.00 (0.00) | 0.09 (0.00) |
| missforest | 0.12 (0.00) | 0.11 (0.00) | 0.00 (0.00) | 0.08 (0.00) |
| missranger | 0.22 (0.01) | 0.15 (0.00) | 0.00 (0.00) | 0.09 (0.01) |
| mixgb | 0.12 (0.00) | 0.11 (0.00) | 0.00 (0.00) | 0.08 (0.00) |
| Continuous, n=1000, Missing Probability = 0.4 | ||||
| jomo | 0.44 (0.01) | 0.29 (0.01) | -0.00 (0.01) | 0.17 (0.00) |
| knn | 0.33 (0.01) | 0.26 (0.00) | 0.00 (0.01) | 0.18 (0.00) |
| merf | 0.37 (0.02) | 0.27 (0.01) | 0.01 (0.01) | 0.16 (0.00) |
| mice_freq | 0.44 (0.01) | 0.30 (0.01) | 0.00 (0.01) | 0.17 (0.00) |
| mice_pmm | 0.44 (0.01) | 0.29 (0.00) | 0.00 (0.01) | 0.17 (0.00) |
| missforest | 0.29 (0.01) | 0.24 (0.01) | 0.01 (0.02) | 0.16 (0.00) |
| missranger | 0.47 (0.01) | 0.30 (0.01) | 0.01 (0.01) | 0.18 (0.01) |
| mixgb | 0.32 (0.02) | 0.25 (0.01) | 0.00 (0.01) | 0.16 (0.00) |
## `summarise()` has grouped output by 'type', 'n_subj', 'miss_prob'. You can
## override using the `.groups` argument.
| Method | diff_mse | diff_mae | diff_bias | diff_aic | diff_auc |
|---|---|---|---|---|---|
| Binary, n=200, Missing Probability = 0.2 | |||||
| jomo | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -3.03 (6.01) | 0.00 (0.00) |
| knn | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -4.32 (6.15) | 0.00 (0.00) |
| merf | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -3.88 (6.34) | 0.00 (0.00) |
| mice_freq | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -2.76 (6.18) | 0.00 (0.01) |
| mice_pmm | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -2.73 (6.40) | 0.00 (0.00) |
| missforest | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -3.68 (6.01) | 0.00 (0.00) |
| missranger | 0.00 (0.00) | 0.00 (0.00) | -0.00 (0.00) | 2.89 (5.36) | -0.00 (0.00) |
| mixgb | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -4.31 (6.05) | 0.00 (0.00) |
| Binary, n=200, Missing Probability = 0.4 | |||||
| jomo | -0.00 (0.00) | -0.00 (0.01) | 0.00 (0.00) | -8.18 (10.98) | 0.01 (0.01) |
| knn | -0.00 (0.00) | -0.01 (0.01) | -0.00 (0.00) | -13.14 (13.02) | 0.01 (0.01) |
| merf | -0.00 (0.00) | -0.00 (0.01) | -0.00 (0.00) | -9.01 (12.32) | 0.01 (0.01) |
| mice_freq | -0.00 (0.00) | -0.00 (0.01) | 0.00 (0.00) | -8.05 (11.36) | 0.01 (0.01) |
| mice_pmm | -0.00 (0.00) | -0.00 (0.01) | -0.00 (0.00) | -7.61 (11.15) | 0.00 (0.01) |
| missforest | -0.00 (0.00) | -0.00 (0.01) | -0.00 (0.00) | -8.37 (11.80) | 0.01 (0.01) |
| missranger | 0.00 (0.00) | 0.00 (0.00) | 0.00 (0.00) | 4.52 (7.17) | -0.00 (0.01) |
| mixgb | -0.00 (0.00) | -0.00 (0.01) | -0.00 (0.00) | -10.52 (11.80) | 0.01 (0.01) |
| Binary, n=500, Missing Probability = 0.2 | |||||
| jomo | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -2.72 (8.68) | 0.00 (0.00) |
| knn | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -7.14 (9.15) | 0.00 (0.00) |
| merf | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -10.35 (11.85) | 0.00 (0.00) |
| mice_freq | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -2.96 (8.57) | 0.00 (0.00) |
| mice_pmm | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -2.27 (8.65) | 0.00 (0.00) |
| missforest | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -10.57 (11.65) | 0.00 (0.00) |
| missranger | 0.00 (0.00) | 0.00 (0.00) | 0.00 (0.00) | 6.98 (7.87) | -0.00 (0.00) |
| mixgb | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -10.74 (10.24) | 0.00 (0.00) |
| Binary, n=500, Missing Probability = 0.4 | |||||
| jomo | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -6.81 (13.95) | 0.00 (0.00) |
| knn | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -21.04 (20.05) | 0.01 (0.01) |
| merf | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -17.31 (21.70) | 0.00 (0.01) |
| mice_freq | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -7.12 (14.12) | 0.00 (0.00) |
| mice_pmm | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -7.66 (14.44) | 0.00 (0.00) |
| missforest | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -15.84 (20.87) | 0.00 (0.01) |
| missranger | 0.00 (0.00) | 0.00 (0.00) | 0.00 (0.00) | 12.20 (10.94) | -0.00 (0.00) |
| mixgb | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -22.88 (19.73) | 0.01 (0.01) |
| Binary, n=1000, Missing Probability = 0.2 | |||||
| jomo | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -2.66 (11.11) | 0.00 (0.00) |
| knn | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -12.02 (12.58) | 0.00 (0.00) |
| merf | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -25.98 (18.72) | 0.00 (0.00) |
| mice_freq | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -2.52 (11.16) | 0.00 (0.00) |
| mice_pmm | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -2.33 (11.78) | 0.00 (0.00) |
| missforest | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -25.45 (18.62) | 0.00 (0.00) |
| missranger | 0.00 (0.00) | 0.00 (0.00) | 0.00 (0.00) | 12.00 (12.07) | -0.00 (0.00) |
| mixgb | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -26.64 (16.23) | 0.00 (0.00) |
| Binary, n=1000, Missing Probability = 0.4 | |||||
| jomo | -0.00 (0.00) | -0.00 (0.00) | 0.00 (0.00) | -7.50 (18.64) | 0.00 (0.00) |
| knn | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -33.43 (26.86) | 0.00 (0.00) |
| merf | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -37.52 (34.24) | 0.00 (0.00) |
| mice_freq | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -7.56 (19.13) | 0.00 (0.00) |
| mice_pmm | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -7.45 (19.66) | 0.00 (0.00) |
| missforest | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -34.36 (32.63) | 0.00 (0.00) |
| missranger | 0.00 (0.00) | 0.00 (0.00) | -0.00 (0.00) | 20.88 (18.76) | -0.00 (0.00) |
| mixgb | -0.00 (0.00) | -0.00 (0.00) | -0.00 (0.00) | -47.97 (30.91) | 0.01 (0.00) |
## `summarise()` has grouped output by 'type', 'n_subj', 'miss_prob'. You can
## override using the `.groups` argument.
| Method | diff_mse | diff_mae | diff_bias | diff_aic | diff_r2 |
|---|---|---|---|---|---|
| Continuous, n=200, Missing Probability = 0.2 | |||||
| jomo | 0.07 (0.04) | 0.03 (0.02) | 0.00 (0.00) | 48.58 (35.94) | -0.00 (0.00) |
| knn | 0.28 (0.04) | 0.11 (0.02) | 0.00 (0.00) | 232.91 (31.11) | -0.02 (0.00) |
| merf | 0.17 (0.04) | 0.07 (0.02) | 0.00 (0.00) | 136.98 (30.12) | -0.01 (0.00) |
| mice_freq | 0.11 (0.04) | 0.05 (0.02) | 0.00 (0.00) | 70.08 (35.08) | -0.01 (0.00) |
| mice_pmm | 0.14 (0.04) | 0.06 (0.02) | -0.00 (0.00) | 89.48 (33.55) | -0.01 (0.00) |
| missforest | 0.16 (0.04) | 0.07 (0.02) | -0.00 (0.00) | 130.88 (30.70) | -0.01 (0.00) |
| missranger | 0.30 (0.05) | 0.12 (0.02) | 0.00 (0.00) | 245.75 (36.01) | -0.02 (0.00) |
| mixgb | 0.09 (0.04) | 0.04 (0.02) | 0.00 (0.00) | 55.81 (33.21) | -0.01 (0.00) |
| Continuous, n=200, Missing Probability = 0.4 | |||||
| jomo | 0.14 (0.06) | 0.06 (0.03) | 0.00 (0.00) | 85.08 (54.88) | -0.01 (0.00) |
| knn | 0.50 (0.06) | 0.19 (0.02) | -0.00 (0.00) | 378.88 (37.17) | -0.03 (0.00) |
| merf | 0.34 (0.06) | 0.13 (0.02) | 0.00 (0.00) | 257.14 (44.31) | -0.02 (0.00) |
| mice_freq | 0.19 (0.06) | 0.08 (0.02) | 0.00 (0.00) | 111.67 (51.92) | -0.01 (0.00) |
| mice_pmm | 0.24 (0.06) | 0.10 (0.02) | 0.00 (0.00) | 145.76 (51.97) | -0.01 (0.00) |
| missforest | 0.33 (0.06) | 0.13 (0.02) | 0.00 (0.00) | 251.95 (43.42) | -0.02 (0.00) |
| missranger | 0.53 (0.07) | 0.20 (0.02) | 0.00 (0.00) | 393.76 (41.35) | -0.03 (0.00) |
| mixgb | 0.22 (0.06) | 0.09 (0.02) | 0.00 (0.00) | 150.49 (49.45) | -0.01 (0.00) |
| Continuous, n=500, Missing Probability = 0.2 | |||||
| jomo | 0.07 (0.03) | 0.03 (0.01) | -0.00 (0.00) | 123.41 (55.04) | -0.00 (0.00) |
| knn | 0.28 (0.03) | 0.11 (0.01) | 0.00 (0.00) | 580.88 (48.27) | -0.02 (0.00) |
| merf | 0.14 (0.02) | 0.06 (0.01) | -0.00 (0.00) | 273.22 (47.94) | -0.01 (0.00) |
| mice_freq | 0.11 (0.02) | 0.05 (0.01) | -0.00 (0.00) | 181.69 (52.07) | -0.01 (0.00) |
| mice_pmm | 0.14 (0.02) | 0.06 (0.01) | -0.00 (0.00) | 231.57 (54.40) | -0.01 (0.00) |
| missforest | 0.13 (0.02) | 0.05 (0.01) | 0.00 (0.00) | 255.47 (48.11) | -0.01 (0.00) |
| missranger | 0.29 (0.03) | 0.11 (0.01) | -0.00 (0.00) | 592.19 (68.52) | -0.02 (0.00) |
| mixgb | 0.04 (0.02) | 0.02 (0.01) | -0.00 (0.00) | 13.77 (50.87) | -0.00 (0.00) |
| Continuous, n=500, Missing Probability = 0.4 | |||||
| jomo | 0.14 (0.04) | 0.06 (0.02) | 0.00 (0.00) | 221.08 (84.58) | -0.01 (0.00) |
| knn | 0.50 (0.04) | 0.19 (0.01) | 0.00 (0.00) | 951.04 (58.22) | -0.03 (0.00) |
| merf | 0.31 (0.04) | 0.12 (0.02) | 0.00 (0.00) | 569.64 (74.49) | -0.02 (0.00) |
| mice_freq | 0.20 (0.04) | 0.08 (0.02) | -0.00 (0.00) | 295.23 (82.94) | -0.01 (0.00) |
| mice_pmm | 0.24 (0.04) | 0.10 (0.01) | 0.00 (0.00) | 371.15 (79.51) | -0.01 (0.00) |
| missforest | 0.30 (0.04) | 0.12 (0.02) | 0.00 (0.00) | 553.12 (77.10) | -0.02 (0.00) |
| missranger | 0.52 (0.05) | 0.20 (0.02) | 0.00 (0.00) | 963.75 (86.85) | -0.03 (0.00) |
| mixgb | 0.13 (0.04) | 0.05 (0.02) | 0.00 (0.00) | 158.64 (89.16) | -0.01 (0.00) |
| Continuous, n=1000, Missing Probability = 0.2 | |||||
| jomo | 0.07 (0.02) | 0.03 (0.01) | 0.00 (0.00) | 245.52 (76.97) | -0.00 (0.00) |
| knn | 0.28 (0.02) | 0.11 (0.01) | 0.00 (0.00) | 1155.32 (69.56) | -0.02 (0.00) |
| merf | 0.12 (0.02) | 0.05 (0.01) | 0.00 (0.00) | 439.92 (74.63) | -0.01 (0.00) |
| mice_freq | 0.11 (0.02) | 0.05 (0.01) | 0.00 (0.00) | 370.60 (77.48) | -0.01 (0.00) |
| mice_pmm | 0.14 (0.02) | 0.06 (0.01) | 0.00 (0.00) | 467.30 (75.16) | -0.01 (0.00) |
| missforest | 0.11 (0.02) | 0.05 (0.01) | 0.00 (0.00) | 403.31 (74.43) | -0.01 (0.00) |
| missranger | 0.28 (0.03) | 0.11 (0.01) | 0.00 (0.00) | 1135.63 (143.65) | -0.02 (0.00) |
| mixgb | 0.01 (0.01) | 0.00 (0.01) | 0.00 (0.00) | -130.35 (75.40) | -0.00 (0.00) |
| Continuous, n=1000, Missing Probability = 0.4 | |||||
| jomo | 0.14 (0.03) | 0.06 (0.01) | 0.00 (0.00) | 442.60 (126.30) | -0.01 (0.00) |
| knn | 0.50 (0.03) | 0.19 (0.01) | 0.00 (0.00) | 1898.47 (80.57) | -0.03 (0.00) |
| merf | 0.29 (0.03) | 0.11 (0.01) | 0.00 (0.00) | 1041.18 (128.70) | -0.02 (0.00) |
| mice_freq | 0.20 (0.03) | 0.08 (0.01) | 0.00 (0.00) | 602.18 (116.18) | -0.01 (0.00) |
| mice_pmm | 0.24 (0.03) | 0.10 (0.01) | 0.00 (0.00) | 743.07 (112.42) | -0.01 (0.00) |
| missforest | 0.27 (0.03) | 0.10 (0.01) | 0.00 (0.00) | 974.14 (128.89) | -0.02 (0.00) |
| missranger | 0.50 (0.05) | 0.19 (0.02) | 0.00 (0.00) | 1867.79 (178.28) | -0.03 (0.00) |
| mixgb | 0.08 (0.03) | 0.03 (0.01) | 0.00 (0.00) | 25.58 (159.86) | -0.00 (0.00) |